Pedro Hermosilla

TU Wien — Austria

Engineering · Physical Sciences

11h-index333citations77works2.42yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

3D Shape Modeling and Analysis(20), Computer Graphics and Visualization Techniques(16), Advanced Neural Network Applications(10), Data Visualization and Analytics(10), Human Pose and Action Recognition(8)

Publications77 total

Style Brush: Guided Style Transfer for 3D Objects
Computer Graphics Forum·2026Open Access
S2D: Sparse-To-Dense Keymask Distillation for Unsupervised Video Instance Segmentation
arXiv (Cornell University)·2025Open Access
Unified Semantic Transformer for 3D Scene Understanding
arXiv (Cornell University)·2025Open Access
Marching Neurons: Accurate Surface Extraction for Neural Implicit Shapes
ACM Transactions on Graphics·2025Open Access
Language-guided 3D scene synthesis for fine-grained functionality understanding
arXiv (Cornell University)·2025Open Access
From Natural to Nanoscale: Training ControlNet on Scarce FIB-SEM Data for Augmenting Semantic Segmentation Data
2025
Style Brush: Guided Style Transfer for 3D Objects
arXiv (Cornell University)·2025Open Access
SoluProtMut: Siamese Deep Learning for Predicting Solubility Effects of Protein Mutations with Experimental Validation
2025Open Access
Marching Neurons: Accurate Surface Extraction for Neural Implicit Shapes
arXiv (Cornell University)·2025Open Access
DeepEM Playground: Bringing deep learning to electron microscopy labs
Journal of Microscopy·2025· 1 citedOpen Access
Exploring Modality Guidance to Enhance VFM-Based Feature Fusion for UDA in 3D Semantic Segmentation
2025
Masked Scene Modeling: Narrowing the Gap Between Supervised and Self-Supervised Learning in 3D Scene Understanding
2025
RelationField: Relate Anything in Radiance Fields
2025
Masked Scene Modeling: Narrowing the Gap Between Supervised and Self-Supervised Learning in 3D Scene Understanding
arXiv (Cornell University)·2025Open Access
TTT-KD: Test-Time Training for 3D Semantic Segmentation Through Knowledge Distillation From Foundation Models
2025
Efficient Continuous Group Convolutions for Local SE(3) Equivariance in 3D Point Clouds
2025
Active Learning Inspired ControlNet Guidance for Augmenting Semantic Segmentation Datasets
arXiv (Cornell University)·2025Open Access
Attention-Guided Masked Autoencoders for Learning Image Representations
2025· 2 cited
Efficient Continuous Group Convolutions for Local SE(3) Equivariance in 3D Point Clouds
arXiv (Cornell University)·2025Open Access
HPSCAN: Human Perception‐Based Scattered Data Clustering
Computer Graphics Forum·2024· 2 citedOpen Access
page 1 of 4Next →

Frequent Co-authors

Timo Ropinski(33), Pere‐Pau Vázquez(15), Tobias Ritschel(9), Àlvar Vinacua(9), Sebastian Koch(6), Narunas Vaškevičius(6), Mirco Colosi(6), Vı́ctor Guallar(6), Michael Schelling(6), Sebastian Hartwig(4), Leon Sick(4), Dominik Engel(4), Hannah Kniesel(4), Barbora Kozlíková(3), Michael Krone(3), Christian van Onzenoodt(3), Renata G. Raidou(3), Lisa Weijler(3), Michael J. Reiter(3), Margarita Maurer‐Granofszky(3)